Cross-IQA: Unsupervised Learning for Image Quality Assessment

arXiv:2405.04311v1 Announce Type: new
Abstract: Automatic perception of image quality is a challenging problem that impacts billions of Internet and social media users daily. To advance research in this field, we propose a no-reference image quality assessment (NR-IQA) method termed Cross-IQA based on vision transformer(ViT) model. The proposed Cross-IQA method can learn image quality features from unlabeled image data. We construct the pretext task of synthesized image reconstruction to unsupervised extract the image quality information based ViT block. The pretrained …

abstract advance arxiv assessment cs.ai cs.cv daily eess.iv image impacts internet learn media perception quality reference research social social media transformer type unsupervised unsupervised learning vision vit